Intelligent door lock abnormal behavior detection method

Abstract

The invention is applicable to the technical field of intelligent door locks, and particularly relates to an intelligent door lock abnormal behavior detection method, which comprises the following steps: acquiring abnormal reason information under the condition of determining that a door lock is abnormal, determining specific values of a plurality of abnormal data of the abnormal reason information based on environment voiceprint data, and determining the abnormal behavior of the door lock according to the specific values. Determining a risk value according to the specific values of the plurality of abnormal data of the abnormal reason information and the corresponding abnormal data, and determining whether to start an emergency measure based on the risk value; the abnormal reason information special value is dynamically adjusted based on the method, the accuracy of risk value output is improved, the accuracy of abnormal judgment is improved, the number of times of starting emergency measures caused by inaccurate abnormal detection in the prior art is reduced, and therefore false alarm information is reduced, the false alarm rate is reduced, and excessive interference to a user is avoided.

Description

Technical Field

[0001] The present application belongs to the technical field of smart door locks, and in particular relates to a method for detecting abnormal behavior of smart door locks. Background Art

[0002] Smart door locks are improvements over traditional mechanical locks, offering enhanced intelligence and simplicity in terms of user security, identification, and manageability. They typically consist of a housing, a panel mounted on the housing, a display screen, a wireless communication module, a lock cylinder, a deadbolt, a lock body, a battery, a motor, sensors, an electromagnetic clutch, and a controller.

[0003] Some smart door locks have built-in anomaly detection functions that can detect abnormal door opening signals and alert the user. However, existing smart door lock anomaly detection methods typically rely on a single sensor to detect a single piece of information, and then determine whether an anomaly exists based on that single piece of information. For example, a vibration sensor detects the force applied to the smart door lock and compares that force with a set fixed threshold to determine whether an anomaly exists. When the fixed threshold is exceeded, the controller immediately triggers an alarm mechanism, such as sending an anomaly message to the user's phone. However, this anomaly detection method suffers from a high false positive rate, resulting in users frequently receiving erroneous alarm messages and causing excessive intrusion. Summary of the Invention

[0004] The embodiment of the present application provides a method for detecting abnormal behavior of a smart door lock, which can solve the problem that traditional smart door locks have a high misjudgment rate, causing users to receive a large number of erroneous alarm messages.

[0005] In a first aspect, an embodiment of the present application provides a method for detecting abnormal behavior of a smart door lock, comprising: When it is determined that the door lock has an abnormality, information about the cause of the abnormality is obtained; wherein the abnormality cause information includes multiple abnormal data, at least two of which are environmental soundprint data and lock tongue force data; the abnormal data is the result of threshold calculation of basic data collected by each sensor and the abnormality cause information; Determining, based on the environmental voiceprint data, unique values ​​of a plurality of the abnormal data of the abnormal cause information; Determine a risk value based on the specific values ​​of the plurality of abnormal data of the abnormal cause information and the corresponding abnormal data; Determining whether to initiate emergency measures is based on the risk value.

[0006] The above technical solutions in the embodiments of the present application have at least the following technical effects: The embodiment of the present application provides a method for detecting abnormal behavior of a smart door lock. When it is determined that an abnormality occurs in the door lock, information on the cause of the abnormality is obtained, and specific values ​​of multiple abnormal data of the abnormal cause information are dynamically determined based on the environmental voiceprint data. A risk value is determined based on the specific values ​​of multiple abnormal data of the abnormal cause information and the corresponding abnormal data. Whether to initiate dynamic emergency measures is determined based on the risk value. The specific value of the abnormal cause information is dynamically adjusted based on the above method to improve the accuracy of the risk value output, so as to improve the accuracy of abnormality judgment and reduce the number of times emergency measures are initiated due to inaccurate abnormality detection in the prior art, thereby reducing false alarm information, reducing the false alarm rate, and avoiding excessive interference to users.

[0007] In a possible implementation of the first aspect, when determining that a door lock is abnormal, obtaining abnormality cause information includes: When it is determined that the door lock is abnormal, activating the sound sensor and the pressure sensor; The sound sensor and the pressure sensor are used to respectively obtain the environmental soundprint data and the lock tongue force data of the abnormal cause information in real time.

[0008] In a possible implementation of the first aspect, determining, based on the environmental voiceprint data, the unique values ​​of the plurality of abnormal data of the abnormal cause information includes: Determining the types of interference options present in the environment where the smart door lock is located based on the environmental voiceprint data; wherein the types of interference options include passing vehicles, renovations, and thunderstorms; The basic values ​​corresponding to the plurality of abnormal data are adjusted based on the interference option type to obtain the specific values ​​of the plurality of abnormal data of the abnormal cause information.

[0009] In a possible implementation of the first aspect, determining the type of interference options present in the environment where the smart door lock is located based on the environmental voiceprint data includes: Performing voiceprint feature extraction based on the environmental voiceprint data to obtain voiceprint feature data of the environmental voiceprint data; Obtaining a voiceprint feature template for each type of interference option type; Obtaining a cross-correlation coefficient between the voiceprint feature data and each of the voiceprint feature templates according to the voiceprint feature data and the voiceprint feature templates; Based on the cross-correlation coefficient, the interference option type corresponding to the environmental voiceprint data is matched in the database; wherein the database includes multiple preset cross-correlation coefficients and corresponding interference option types.

[0010] In a possible implementation of the first aspect, obtaining the interference option type corresponding to the environmental voiceprint data in a database based on the cross-correlation coefficient includes: When the interference option type corresponding to the environmental voiceprint data is found to be decoration based on the cross-correlation coefficient, a corresponding time domain signal is determined according to the lock tongue force data, and a corresponding time domain signal is determined according to the environmental voiceprint data; Performing a fast Fourier transform based on the time domain signal of the lock tongue force data and the time domain signal of the environmental soundprint data to obtain the frequency spectrum data of the lock tongue force data and the frequency spectrum data of the environmental soundprint data when the interference option type is decoration; Draw corresponding spectrum curves based on the spectrum data of the lock tongue force data and the spectrum data of the environmental voiceprint data; The decoration interference type of the environment where the smart door lock is located is determined according to the spectrum curve corresponding to the spectrum data of the lock tongue force data and the spectrum data of the environmental soundprint data, and the decoration interference type includes: near-point decoration interference and far-point decoration interference.

[0011] In a possible implementation of the first aspect, adjusting base values ​​corresponding to the plurality of abnormal data based on the interference option type to obtain specific values ​​of the plurality of abnormal data of the abnormal cause information includes: When the decoration interference type is near-point decoration interference, adjusting the base values ​​of the environmental soundprint data and the lock tongue force data based on a set environmental soundprint threshold and a set lock tongue force threshold, respectively, to obtain a specific value of the environmental soundprint data and a specific value of the lock tongue force data; In the case where the decoration interference type is far-point decoration interference, the actual environmental soundprint threshold of the environmental soundprint data and the actual lock tongue force threshold of the lock tongue force data are obtained according to the spectrum curve, and the basic values ​​of the environmental soundprint data and the lock tongue force data are adjusted based on the actual environmental soundprint threshold and the actual lock tongue force threshold to obtain the specific value of the environmental soundprint data and the specific value of the lock tongue force data.

[0012] In a possible implementation of the first aspect, adjusting base values ​​corresponding to the plurality of abnormal data based on the interference option type to obtain specific values ​​of the plurality of abnormal data for the abnormal cause information further includes: determining, based on the interference option type, from among the abnormal data, the abnormal data associated with the interference option type; determining an abnormal behavior degree value according to the abnormal data associated with the interference option type; The basic value corresponding to the abnormal data associated with the interference option type is adjusted based on the abnormal behavior degree value to obtain multiple specific values ​​of the abnormal data of the abnormal cause information.

[0013] In a possible implementation of the first aspect, determining the abnormal behavior degree value according to the abnormal data associated with the interference option type includes: determining a relative error of the abnormal data associated with the interference option type according to an absolute value of a difference between the abnormal data associated with the interference option type and a corresponding preset threshold, and a ratio of the abnormal data associated with the interference option type to the corresponding preset threshold; A normalization process is performed based on the relative error to determine an abnormal behavior degree value.

[0014] In a possible implementation of the first aspect, determining a risk value according to the specific values ​​of the plurality of abnormal data in the abnormal cause information and the corresponding abnormal data includes: Determine the abnormality score data corresponding to each abnormal data based on each abnormal data of the abnormal cause information; A risk value is determined based on the specific values ​​of the plurality of abnormal data and the abnormality score data of each abnormal data in the abnormal cause information.

[0015] In a possible implementation of the first aspect, determining whether to initiate emergency measures based on the risk value includes: Performing a difference analysis based on the risk value and a preset threshold to obtain a risk abnormality deviation of the abnormal data; Based on the risk abnormal deviation, determine whether to initiate emergency measures.

[0016] In a possible implementation of the first aspect, the method further includes: Determining to initiate emergency measures based on the abnormal deviation of the risk; Discretization is performed according to the risk abnormal deviation to obtain a dynamic response curve; Obtaining a dynamic protection characteristic value based on filtering and fusion of the dynamic response curve; The emergency measure level is determined by comparing the dynamic protection characteristic value with a preset range.

[0017] In a second aspect, an embodiment of the present application provides a smart door lock abnormal behavior detection device, which is applied to a smart door lock, wherein the smart door lock includes a door lock body, a sound sensor provided on the door lock body, and a pressure sensor provided on a lock tongue of the door lock body. The smart door lock abnormal behavior detection device includes: a determination unit, configured to obtain abnormality cause information when determining that an abnormality occurs in the door lock; wherein the abnormality cause information includes a plurality of abnormality data, at least two of which are environmental soundprint data and lock tongue force data; An analyzing unit, configured to determine, based on the environmental voiceprint data, specific values ​​of a plurality of the abnormal data of the abnormal cause information; a detection unit, configured to determine a risk value according to the specific values ​​of the plurality of abnormal data of the abnormal cause information and the corresponding abnormal data; A result unit is used to determine whether to initiate an emergency measure based on the risk value.

[0018] In the third aspect, an embodiment of the present application provides a smart door lock, including a door lock body, a controller, a sound sensor arranged on the door lock body, and a pressure sensor arranged on the lock tongue of the door lock body, the controller being electrically connected to the sound sensor and the pressure sensor, respectively, the controller including a memory, a processor, and a computer program stored in the memory and runnable on the processor, and the processor implementing any one of the methods described in the first aspect above when executing the computer program.

[0019] It can be understood that the beneficial effects of the second to third aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0021] Figure 1 Schematic diagram of the structure of a smart door lock to which the smart door lock abnormal behavior detection method provided in one embodiment of the present application is applicable; Figure 2 This is a flow chart of a method for detecting abnormal behavior of a smart door lock provided in one embodiment of the present application; Figure 3 This is a schematic diagram of the spectrum of decoration interference types in the smart door lock abnormal behavior detection method provided by an embodiment of the present application; Figure 4 Schematic diagram of an execution of a method for detecting abnormal behavior of a smart door lock provided in one embodiment of the present application; Figure 5 Schematic diagram of the structure of the intelligent door lock abnormal behavior detection device provided in an embodiment of the present application; Figure 6It is a structural diagram of the smart door lock provided in an embodiment of the present application. DETAILED DESCRIPTION

[0022] In the following description, specific details such as specific system structures and techniques are provided for purposes of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obscuring the description of the present application with unnecessary detail.

[0023] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0024] It will also be understood that the term "and / or" used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0025] As used in this specification and the appended claims, the term "if" can be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0026] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0027] References to "one embodiment" or "some embodiments" in this specification mean that a particular feature, structure, or characteristic described in conjunction with that embodiment is included in one or more embodiments of the present application. Thus, phrases such as "in one embodiment," "in some embodiments," "in other embodiments," and "in other embodiments" appearing in various places in this specification do not necessarily refer to the same embodiment, but rather mean "one or more but not all embodiments," unless otherwise specifically emphasized. The terms "including," "comprising," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0028] Some smart door locks have built-in anomaly detection functions that can detect abnormal door opening signals and alert the user. However, existing smart door lock anomaly detection methods typically rely on a single sensor to detect a single piece of information, and then determine whether an anomaly exists based on that single piece of information. For example, a vibration sensor detects the force applied to the smart door lock and compares that force with a set fixed threshold to determine whether an anomaly exists. When the fixed threshold is exceeded, the controller immediately triggers an alarm mechanism, such as sending an anomaly message to the user's phone. However, this anomaly detection method suffers from a high false positive rate, resulting in users frequently receiving erroneous alarm messages and causing excessive intrusion.

[0029] To solve the above problems, an embodiment of the present application provides a method for detecting abnormal behavior of a smart door lock. In this method, when it is determined that an abnormality has occurred in the door lock, information on the cause of the abnormality is obtained, wherein the abnormal cause information includes multiple abnormal data, at least two of which are environmental soundprint data and lock tongue force data. The specific values ​​of the multiple abnormal data of the abnormal cause information are dynamically determined based on the environmental soundprint data. The risk value is determined based on the specific values ​​of the multiple abnormal data of the abnormal cause information and the corresponding abnormal data, and whether to initiate dynamic emergency measures is determined based on the risk value. Based on the above method, the specific value of the abnormal cause information is dynamically adjusted to improve the accuracy of the risk value output, so as to improve the accuracy of the abnormality judgment and reduce the number of times the emergency measures are initiated due to inaccurate abnormality detection in the prior art, thereby reducing false alarm information, reducing the false alarm rate, and avoiding excessive interference to users. The smart door lock abnormal behavior detection method provided in the embodiment of the present application can be applied to a smart door lock. In this case, the smart door lock is the executor of the smart door lock abnormal behavior detection method provided in the embodiment of the present application. The embodiment of the present application does not impose any restrictions on the specific type of the smart door lock.

[0030] See also Figure 1 For example, the smart door lock 100 may include a door lock body 10, a controller 20, a sound sensor 30 arranged on the door lock body, and a pressure sensor 40 arranged on the lock tongue of the door lock body. The controller 20 is electrically connected to the sound sensor 30 and the pressure sensor 40 respectively.

[0031] The door lock body 10 is the main part of the smart door lock, and can be the main part of various existing types of smart door locks. For example, it may include a door lock housing 11, a lock cylinder 12, a lock tongue 13, a handle 14, a motor, a panel 16, a display screen 17, a portrait sensor 18, and a capacitive touch sensor 19. The lock cylinder 12 is arranged inside the door lock housing 11 and is connected to the lock tongue 13 to drive the lock tongue 13 to move. The handle 14 is connected to the lock cylinder 12. The motor is arranged inside the door lock housing 11 and is connected to the lock cylinder 12 to drive the lock cylinder 12. The panel 16, the display screen 17, the portrait sensor 18, and the capacitive touch sensor 19 are arranged on the door lock housing 11. The controller 20 is electrically connected to the motor 15, the panel 16, the display screen 17, the portrait sensor 18, and the capacitive touch sensor 19 respectively.

[0032] The sound sensor can be any type of sensor capable of receiving sound waves and can be installed at any position of the door lock body, for example, on the door lock housing. The sound sensor is used to detect the sound intensity and sound waveform and transmit the detected data to the controller.

[0033] The pressure sensor may be any of various types of sensors capable of detecting force, and may be disposed on a surface surrounding the axis of the bolt to transmit the detected data to the controller.

[0034] The controller is the control part in the smart door lock, which can be an integrated circuit board on which computing units such as a main control chip and a microcontroller can be arranged.

[0035] In order to better understand the smart door lock abnormal behavior detection method provided in the embodiment of the present application, the specific implementation process of the smart door lock abnormal behavior detection method provided in the embodiment of the present application is exemplarily introduced below.

[0036] Figure 2 The following is a schematic flow chart of a method for detecting abnormal behavior of a smart door lock provided in an embodiment of the present application. The method for detecting abnormal behavior of a smart door lock includes: S100, when it is determined that the door lock has an abnormality, obtain abnormality cause information; wherein the abnormality cause information includes multiple abnormal data, at least two of which are environmental voiceprint data and lock tongue force data.

[0037] It can be understood that environmental soundprint data is data that quantifies and digitally represents the characteristics of sound in the environment, such as sound intensity and waveform. Lock tongue force data is related to the data generated when the lock tongue is subjected to various external forces, such as the force exerted by the handle on the lock tongue ..., such as the force exerted by the handle, such as the force exerted by the handle, such as

[0038] Door lock abnormality means that the door lock deviates from its normal working state during use, for example: face recognition fails three or more times in a row, password verification fails three or more times in a row, fingerprint recognition fails three or more times in a row, the sound sensor detects that the preset threshold is exceeded, and the pressure sensor on the lock tongue detects that the preset threshold is exceeded.

[0039] As an optional embodiment of the present application, in S100, when it is determined that the door lock is abnormal, obtaining abnormality cause information includes: S110 , when it is determined that the door lock is abnormal, the sound sensor and the pressure sensor are activated.

[0040] It is understood that the controller usually has a built-in abnormality detection module. When at least one of the following abnormal conditions occurs, such as facial recognition failure three or more times in a row, password verification failure three or more times in a row, fingerprint recognition failure three or more times in a row, the sound sensor detection exceeds the preset threshold, or the pressure sensor on the lock tongue detects that the value exceeds the preset threshold, the activation command will be immediately triggered. This command can be sent to the control circuit of the sound sensor and pressure sensor through the main control chip of the door lock, causing the sensors that were originally in low-power or dormant state to quickly enter the working mode and begin real-time data collection.

[0041] S120, obtaining in real time environmental voiceprint data and lock tongue force data of abnormality cause information through a sound sensor and a pressure sensor respectively.

[0042] As you can understand, the sound sensor can detect unusual noises around the door lock, such as those caused by renovations, thunder during a thunderstorm, and horns from passing vehicles. The pressure sensor can monitor changes in pressure on the door lock, recording data on the lock tongue's pressure, such as when the door lock is violently impacted. The data collected by both sensors is transmitted in real time to the controller for analysis and processing.

[0043] By implementing steps S110 to S120, if an abnormality is detected in the door lock, the sound sensor and pressure sensor are promptly activated, allowing the sensors, which were originally in a low-power state, to quickly enter an operating mode and begin real-time data collection. Real-time abnormal data outside the door lock is obtained, improving the door lock controller's ability and speed to promptly obtain abnormal data when subjected to external impacts.

[0044] S200, determining unique values ​​of multiple abnormal data of abnormal cause information based on environmental voiceprint data.

[0045] It can be understood that the specific value is a value indicating the importance of the corresponding abnormal data in the controller.

[0046] For example, the environmental interference options can be determined by analyzing and matching the environmental voiceprint data, and the environmental voiceprint data with abnormal cause information can be obtained in real time to determine the specific value.

[0047] As an optional embodiment of the present application, S200, determining the unique values ​​of each of the plurality of abnormal data of the abnormal cause information based on the environmental voiceprint data, includes: S210, determining the types of interference options in the environment where the smart door lock is located based on the environmental voiceprint data; wherein the interference option types include passing vehicles, decoration and thunderstorm weather.

[0048] Exemplarily, the controller pre-stores environmental soundprint data corresponding to different interference option types such as passing vehicles, decoration, thunderstorm weather, etc.

[0049] For example, the voiceprint data of a passing vehicle may include features such as the roar of the engine, the friction between the tires and the ground, and the sound of the vehicle horn. The parameters such as the frequency, intensity, and duration of these sounds have certain patterns.

[0050] The sounds produced by decoration, such as electric drills, hammers, electric saws, etc., usually have high intensity and specific frequency range, and the sounds are relatively continuous and regularly intermittent.

[0051] The voiceprint data of thunderstorm weather is characterized by the low frequency and high intensity of thunder and the static sound accompanying lightning. There may also be background sounds such as wind and rain as auxiliary features.

[0052] When new environmental voiceprint data is input, the controller will compare it with these known feature models to determine whether the new environmental voiceprint data is a pre-stored interference option type.

[0053] In one possible implementation, S210, determining the type of interference options in the environment where the smart door lock is located based on the environmental voiceprint data, includes: S211, performing voiceprint feature extraction based on the environmental voiceprint data to obtain voiceprint feature data of the environmental voiceprint data.

[0054] It can be understood that voiceprint feature data is specific data extracted from the voiceprint, such as the sound intensity and sound waveform. The voiceprint feature data obtained after transformation is usually presented in the form of a set of numerical vectors or parameter sets with a specific format and dimension. For example, it can be a single-frame MFCC (Mel-frequency cepstral coefficient) feature: [c1, c2, ..., c13] (13-dimensional vector, containing 12th-order MFCC coefficients + 1st-order energy).

[0055] Technically, various algorithms and signal processing techniques are used to extract voiceprint features. A common method is the Short-Time Fourier Transform (STFT), which converts time-domain sound signals into the frequency domain and analyzes the frequency components of the sound at different time points. This method can extract voiceprint features such as frequency, amplitude, and harmonics from environmental voiceprint data.

[0056] S212: Obtain a voiceprint feature template for each type of interference option type.

[0057] It's understood that a voiceprint feature template is a specific voiceprint feature representing the types of interference options. It's a template within a fixed range, such as a fixed range of sound intensity or sound waveform. The voiceprint feature template is pre-set in the door lock controller and can be directly accessed when needed.

[0058] S213: Obtain a cross-correlation coefficient between the voiceprint feature data and each voiceprint feature template according to the voiceprint feature data and the voiceprint feature template.

[0059] As you can understand, the cross-correlation coefficient is a metric used to measure the similarity between two signals (in this case, the voiceprint feature data and the signal represented by the voiceprint feature template). Its value ranges from -1 to 1. When the cross-correlation coefficient is 1, it indicates that the two signals are identical; when it is -1, it indicates that the two signals are completely opposite; when it is 0, it indicates that there is no correlation between the two signals. In the context of voiceprint analysis, the cross-correlation coefficient is used to determine the degree of similarity between the voiceprint features of the current ambient sound and the voiceprint feature templates of various interference options.

[0060] Calculate the mean of vectors X and Y: Mean of X , Mean of Y ; Calculate the numerator part: The numerator is the covariance of X and Y, and the calculation formula is: Calculate the denominator: The denominator is the product of the standard deviations of X and Y: Standard deviation of X , Standard deviation of Y ; The denominator is ; Calculate the cross-correlation coefficient (Pearson correlation coefficient): Through the above steps, we can get the cross-correlation coefficient between the voiceprint feature data X and the voiceprint feature template Y. For other different voiceprint feature templates, repeat the above calculation process to get the cross-correlation coefficient between the voiceprint feature data and each voiceprint feature template.

[0061] S214, matching the interference option type corresponding to the environmental voiceprint data in the database based on the cross-correlation coefficient; wherein the database includes a plurality of preset cross-correlation coefficients and corresponding interference option types.

[0062] It can be understood that based on the calculated cross-correlation coefficient, the controller will search and match in the database. Specifically, the obtained cross-correlation coefficient is compared with the various preset cross-correlation coefficients stored in the database to find the closest preset value. By finding the closest preset cross-correlation coefficient, the corresponding interference option type can be determined, and this type is the interference option type corresponding to the current environmental voiceprint data. For example, if the calculated cross-correlation coefficient is 0.85, and the interference option type corresponding to the range of 0.8-1.0 in the database is "decoration", then it can be determined that the interference option type corresponding to the current environmental voiceprint data is "decoration".

[0063] By adopting the above steps S211 to S214, it is helpful to accurately identify the type of environmental interference options. By matching the voiceprint feature template with the real-time voiceprint feature data, the cross-correlation coefficient is obtained, thereby improving the suitability and stability of the smart door lock and enhancing the ability of the smart door lock to identify the type of interference options.

[0064] Optionally, in S214, obtaining the interference option type corresponding to the environmental voiceprint data by matching in the database based on the cross-correlation coefficient includes: S2141, when the interference option type corresponding to the environmental voiceprint data obtained by matching in the database based on the cross-correlation coefficient is decoration, the corresponding time domain signal is determined according to the lock tongue force data, and the corresponding time domain signal is determined according to the environmental voiceprint data.

[0065] It can be understood that when the interference option type corresponding to the environmental voiceprint data obtained by matching the cross-correlation coefficient in the database is decoration, the lock tongue force data is collected in real time by the pressure sensor installed on the lock tongue. These data reflect the magnitude of the force exerted on the lock tongue at different times. By arranging and analyzing these time-varying lock tongue force data in chronological order, the corresponding time domain signal can be obtained. In the time domain signal, the horizontal axis represents time and the vertical axis represents the magnitude of the force exerted on the lock tongue. Through this time domain signal, it is possible to intuitively observe how the force exerted on the lock tongue changes over time during the decoration period, such as whether there is a sudden force exerted on the smart door lock due to decoration operations.

[0066] Ambient soundprint data is converted from ambient sounds collected by sound sensors. It includes the sound characteristics of various tools used during renovations, such as drills and hammers. Similarly, by processing and analyzing this soundprint data in chronological order, we can generate the corresponding time domain signal. This time domain signal shows how the intensity of renovation sounds changes over time. For example, the time domain signal shows the start and end times, duration, and fluctuations in the intensity of different renovation sounds.

[0067] S2142 , performing fast Fourier transform based on the time domain signal of the lock tongue force data and the time domain signal of the environmental soundprint data, to obtain the frequency spectrum data of the lock tongue force data and the frequency spectrum data of the environmental soundprint data when the interference option type is decoration.

[0068] It can be understood that the frequency spectrum of the lock tongue force data represents the frequency spectrum of the lock tongue force data obtained by performing a fast Fourier transform on the time domain signal of the lock tongue force data. By analyzing this frequency spectrum data, we can understand the distribution of forces of different frequencies within the external forces acting on the lock tongue under the interference of renovations. For example, whether there is a prominent external force component of a specific frequency may be related to the vibration frequency of the renovation tools, thereby further determining the manner and extent of the impact of the renovation activity on the lock tongue.

[0069] Similarly, the spectrum data of the ambient soundprint data represents the spectrum data obtained by performing a Fast Fourier Transform on the time-domain signal of the ambient soundprint data. This spectrum data reflects the distribution and intensity of the various frequency components in the renovation sounds. For example, different renovation sounds such as the sound of an electric drill and the sound of a hammer will have unique frequency signatures on the spectrum. By analyzing this spectrum data, we can more accurately identify the composition and characteristics of the renovation sounds and their impact on the acoustic environment around the door lock.

[0070] S2143 , drawing corresponding spectrum curves based on the spectrum data of the lock tongue force data and the spectrum data of the environmental voiceprint data.

[0071] A spectrum curve is a data graph drawn based on the frequency spectrum of the lock tongue force data. It typically plots frequency on the horizontal axis and the amplitude corresponding to each frequency on the vertical axis. In a rectangular coordinate system, the points corresponding to each frequency and amplitude in the spectrum data are marked, and then connected with a smooth curve to form the spectrum curve of the lock tongue force data. This curve allows you to intuitively see the relative strengths of the different frequency components in the lock tongue force signal, as well as which frequency components are more prominent.

[0072] Similarly, for the spectrum data of the environmental soundprint data, the same method is used to plot the spectrum curve of the environmental soundprint data, with frequency as the horizontal axis and amplitude as the vertical axis. This curve can clearly show the distribution of various frequency sounds in the environmental sound, such as the intensity changes of certain high-frequency sounds or low-frequency sounds.

[0073] S2144: Determine the type of decoration interference in the environment where the smart door lock is located based on the spectrum curves corresponding to the spectrum data of the lock tongue force data and the spectrum data of the environmental soundprint data. The types of decoration interference include: near-point decoration interference and far-point decoration interference.

[0074] It can be understood that near-point renovation interference refers to the various impacts of renovation activities on the surrounding environment, people, or facilities within a relatively close distance. Far-point renovation interference refers to the indirect impact of renovation activities on the target area at a relatively long distance.

[0075] By comparing and analyzing the characteristics of the frequency spectrum curve of the lock tongue force data and the frequency spectrum curve of the environmental soundprint data, such as the distribution of frequency components, intensity, peak position, etc., the controller can comprehensively determine the type of decoration interference in the environment where the smart door lock is located. Figure 3 For example, if both spectrum curves show strong high-frequency components and greater intensity, then it may be interference from nearby decoration; if the high-frequency components in the spectrum curve are weak, the overall intensity is low, and the low-frequency components are relatively prominent, then it is more likely to be interference from far-point decoration.

[0076] Near-point interference: The spectrum curve has obvious peaks in the high-frequency band (such as 2000-5000 Hz), and the overall curve is steep with high amplitude.

[0077] Far-point interference: The spectrum curve rises gently in the low-frequency band (such as 100-500 Hz), has no significant peaks in the high-frequency band, and has a low overall amplitude.

[0078] By adopting the above steps S2141 to S2144, it is helpful to distinguish various situations when there is interference from the decoration environment. For example, the spectrum curve in the low frequency band is far-point decoration interference, and the spectrum curve in the high frequency band is near-point decoration interference, thereby improving the door lock's ability to identify external abnormal interference information.

[0079] S220 , adjusting the basic values ​​corresponding to the plurality of abnormal data based on the interference option type to obtain the specific values ​​of the plurality of abnormal data of the abnormal cause information.

[0080] It can be understood that a baseline value represents the value or reference range that the data should have under normal circumstances (no interference or standard conditions). For example, the normal range of lock tongue force in the absence of any interference can be a baseline value. A specific value refers to the data after the baseline value is adjusted, and the adjusted baseline value is determined to be a specific value. For example, if there is no interference option, the baseline value remains unchanged. If there is an interference option, the baseline value is adjusted according to a preset program. These base values ​​determined by the controller's preset program can be identified as specific values. Based on the determined interference option type, the smart door lock will adjust the baseline values ​​corresponding to multiple abnormal data. This is because different interference types can cause the baseline value of the data under normal conditions to change. For example, if the interference option type is renovation, the noise and vibration generated by the renovation may change the normal range of lock tongue force. In this case, the baseline value of the lock tongue force data needs to be adjusted accordingly based on the characteristics and degree of the renovation interference. This may expand or narrow the range of the baseline value, or change the specific value of the baseline value.

[0081] See also Figure 4 In one possible implementation, S220 adjusts the base values ​​corresponding to the plurality of abnormal data based on the interference option type to obtain the specific values ​​of the plurality of abnormal data of the abnormal cause information, including: S221, when the decoration interference type is near-point decoration interference, the basic values ​​of the environmental soundprint data and the lock tongue force data are adjusted based on the set environmental soundprint threshold and the set lock tongue force threshold, to obtain the specific value of the environmental soundprint data and the specific value of the lock tongue force data.

[0082] It can be understood that the environmental soundprint threshold is a standard value or range determined by comprehensively considering the various sound characteristics that may be generated during nearby decoration (such as the intensity of the sound, the frequency range of the sound, etc.), and is used to measure the state of the environmental sound; the lock tongue force threshold is a measurement standard set based on the external force that may be applied to the door lock tongue by nearby decoration (such as the size of the external force, the change in direction, etc.).

[0083] The basic values ​​of the environmental voiceprint data and the lock tongue force data are adjusted respectively to obtain the specific value of the environmental voiceprint data and the specific value of the lock tongue force data. This is achieved by normalizing the ratios of the environmental voiceprint data and the lock tongue force data to the set environmental voiceprint threshold and the set lock tongue force threshold, and then adding the basic values ​​of the environmental voiceprint data and the lock tongue force data respectively to obtain the specific value of the environmental voiceprint data and the specific value of the lock tongue force data.

[0084] Steps to calculate the unique value: Step 1: Input parameters Original data: (Environmental voiceprint data Or lock tongue force data Threshold: (Set the ambient sound pattern threshold or lock tongue force threshold) Base Value: Normalization range: minimum / maximum value of historical ratio ,in Scale factor: (Adjust the sensitivity of the specific value to abnormalities, The value should be less than 1- , greater than 0) Step 2: Calculate the ratio r Constraints: like (Historical data has no fluctuations), it is necessary to set a minimum value to avoid the denominator being 0 (such as ).

[0085] Step 3: Calculate the specific value Special value formula: Special value = .

[0086] Example calculation: Scenario setting: Voiceprint threshold , basic value , proportional coefficient Historical data range: , Calculate historical ratio range: , Case 1: Normal data Ratio calculation: Normalization: Singular value: Singular value .

[0087] S222, when the decoration interference type is far-point decoration interference, the actual environmental soundprint threshold of the environmental soundprint data and the actual lock tongue force threshold of the lock tongue force data are obtained according to the spectrum curve, and the basic values ​​of the environmental soundprint data and the lock tongue force data are adjusted based on the actual environmental soundprint threshold and the actual lock tongue force threshold, so as to obtain the specific value of the environmental soundprint data and the specific value of the lock tongue force data.

[0088] It can be understood that the actual environmental soundprint threshold is obtained by analyzing the spectral curve of previously obtained environmental soundprint data. The spectral curve displays the distribution and intensity of various frequency components in the ambient sound. Due to the characteristics of sound propagation under distant renovation interference (such as the increased attenuation of high-frequency components), the spectral curve can be used to analyze the reasonable range of ambient sound intensity, frequency, and other characteristics corresponding to distant renovation interference. The actual lock tongue force threshold is determined based on the spectral curve of the lock tongue force data. Under distant renovation interference, the vibration and impact force transmitted to the door lock are relatively small and attenuated. The spectral curve reflects the frequency and intensity characteristics of the lock tongue force under this condition. By analyzing these characteristics, the reasonable range of lock tongue force under distant renovation interference can be determined, namely the actual lock tongue force threshold. For example, the maximum fluctuation range of the external force applied to the lock tongue during distant renovation interference can be determined as part of the actual lock tongue force threshold.

[0089] The environmental sound pattern data and lock tongue force data are converted into frequency domain data. The core formula is discrete Fourier transform (DFT): : Time domain signal sampling point; : Frequency domain amplitude, corresponding to frequency component ( is the sampling rate); : is a complex exponential basis function, representing the sinusoidal component with frequency k.

[0090] Extract the amplitude distribution of high frequency bands (such as >500Hz) and low frequency bands (such as <200Hz) in the spectrum curve; - Calculate the total sound pressure level (SPL) or vibration acceleration level: , (reference sound pressure); The statistical method for determining the environmental voiceprint threshold and the lock tongue force threshold is to establish a probability distribution model (such as normal distribution) based on the spectral characteristics of historical data, and calculate the actual environmental voiceprint threshold and the actual lock tongue force threshold: the actual environmental voiceprint threshold or the actual lock tongue force threshold = ; : The mean of characteristic values ​​(such as high frequency amplitude and total sound pressure level); : standard deviation; : Safety factor (e.g. 2 or 3, corresponding to 95% or 99.7% confidence interval).

[0091] Based on the actual environmental soundprint threshold, the baseline value of the environmental soundprint data is adjusted. The baseline value is a reference value or range for environmental soundprint data under normal circumstances (no interference or standard conditions). Due to the presence of distant decoration interference, the original baseline value no longer reflects the actual situation. Based on the actual environmental soundprint threshold, the value or range of the baseline value may be adjusted accordingly to make it more accurately reflect the normal state of environmental soundprint data under distant decoration interference.

[0092] The base value of the lock tongue force data is adjusted based on the actual lock tongue force threshold. Taking into account the impact of distant decoration interference on the lock tongue force, the base value of the lock tongue force data is adjusted to adapt to the lock tongue force characteristics under such interference.

[0093] Based on the actual environmental voiceprint threshold and the actual lock tongue force threshold, the basic values ​​of the environmental voiceprint data and the lock tongue force data are adjusted respectively to obtain the specific value of the environmental voiceprint data and the specific value of the lock tongue force data. The calculation steps are the same as the above-mentioned specific value of the near-point decoration interference. Different thresholds need to be adjusted according to the actual data.

[0094] By implementing steps S221 to S222, the corresponding base values ​​are adjusted based on the actual thresholds of near-point and far-point decoration interference in the decoration scene, thereby obtaining the specific value of the environmental voiceprint data and the specific value of the lock tongue force data. This allows the controller to more accurately obtain the specific value of the abnormal data by analyzing the abnormality cause information.

[0095] Exemplarily, S220, adjusting the base values ​​corresponding to the plurality of abnormal data based on the interference option type to obtain the specific values ​​of the plurality of abnormal data of the abnormal cause information, further includes: S223 : Determine abnormal data associated with the interference option type from among the abnormal data based on the interference option type.

[0096] It can be understood that the abnormal data associated with the interference option type refers to abnormal data that is found through analysis to be related to the interference option type preset by the controller and can reflect the characteristics of the interference option type.

[0097] For example, if the interference option type is "renovation," then the distinctive sounds produced during renovations (reflected in the ambient soundprint data) and the force changes on the door lock tongue caused by possible vibrations from renovations (reflected in the tongue force data) are abnormal data associated with the "renovation" interference option type. Identifying this associated data facilitates more targeted analysis of the door lock's status and possible causes of abnormalities under specific interference conditions, allowing for appropriate response and resolution.

[0098] S224: Determine the abnormal behavior degree value according to the abnormal data associated with the interference option type.

[0099] It can be understood that the abnormal behavior degree value is a quantitative indicator used to measure the degree of abnormality exhibited by the door lock or its surrounding environment under a specific interference option type. By determining this value, you can more intuitively understand the severity of the current situation so that you can take appropriate measures later. When specifically determining the abnormal behavior degree value, it is necessary to comprehensively analyze the abnormal data associated with the interference option type. For example, a strong abnormal sound signal in the environmental voiceprint data contributes more to the abnormal behavior degree value than a slight sound change; and a larger force fluctuation in the lock tongue force data can increase the abnormal behavior degree value more than a small force change.

[0100] In one possible implementation, S224, determining the abnormal behavior degree value based on the abnormal data associated with the interference option type, includes: S2241 , determining a relative error of the abnormal data associated with the interference option type according to the ratio of the absolute value of the difference between the abnormal data associated with the interference option type and the corresponding preset threshold to the corresponding preset threshold.

[0101] It can be understood that the relative error is the ratio of the absolute value of the difference between the abnormal data associated with the interference option type and the corresponding preset threshold to the corresponding preset threshold. It quantifies the degree of deviation of the abnormal data from the preset threshold in a proportional form. For example, it can be the absolute value of the abnormal data minus the threshold divided by the threshold. The larger the relative error, the greater the difference between the abnormal data and the preset normal range, which means that the abnormality reflected by the current data is more obvious.

[0102] S2242: Perform normalization processing based on the relative error to determine the abnormal behavior degree value.

[0103] Normalization is a data processing method that aims to convert data of varying scales and magnitudes into a unified, standardized range, typically the interval [0, 1], but other ranges are possible. Normalization eliminates the effects of differences in scale or value range between data, making them comparable.

[0104] Comprehensive analysis obtained the relative error of abnormal data that interfered with the association of option types ,The following is an example of determining the abnormal behavior degree value based on relative error normalization The formula is: in, is the minimum value among all relative errors, is the maximum value among all relative errors. The function of this formula is to convert the relative error Mapped to the interval [0,1]. hour, , indicating the lowest level of abnormal behavior; when hour, , indicating the highest level of abnormal behavior. value, will be based on its and The position between them is calculated proportionally. For example, if the calculated relative errors are 0.2, 0.5, and 0.8 respectively, then , For relative error , its abnormal behavior degree value .

[0105] By adopting the above steps S2241 to S2242, determining the relative error of the abnormal data associated with the interference option type, and then normalizing the relative error, it is helpful to obtain a more accurate abnormal behavior degree value.

[0106] S225: Based on the abnormal behavior degree value, the basic value corresponding to the abnormal data associated with the interference option type is adjusted to obtain the specific values ​​of multiple abnormal data of the abnormal cause information.

[0107] It can be understood that based on the obtained abnormal behavior degree value, the basic value corresponding to the abnormal data associated with the interference option type is adjusted. If the abnormal behavior degree value is high, it means that the abnormal situation is more serious, and the range of the basic value may be expanded or changed accordingly to adapt to this abnormal situation. For example, when the abnormal behavior degree value of the lock tongue force data is large, the upper limit of the basic value of the lock tongue force data may be increased, because under such interference, the lock tongue force may be greater than normal. Conversely, if the abnormal behavior degree value is low, the basic value may be adjusted slightly or remain unchanged. For example: Linear adjustment model formula: , where B is the base value, D is the abnormality value, and S is the specific value. Is the adjustment coefficient (needs to be set according to the scene, such as Example: Baseline value , abnormality value point, , unique values: When the anomaly is more serious (D=5), the upper limit of the lock tongue force is adjusted from 0.4 to 0.6, allowing a larger vibration amplitude.

[0108] By adopting the above steps S221 to S225, it is helpful to determine the abnormal behavior degree value through the abnormal data associated with the interference option type, adjust the corresponding basic value based on the abnormal behavior degree value of the interference option type, and obtain the corresponding specific value.

[0109] S300, determining a risk value based on the specific values ​​of multiple abnormal data of the abnormal cause information and the corresponding abnormal data; It can be understood that the risk value is a quantitative assessment of the security status of the smart door lock. The higher the risk value, the greater the potential risk faced by the door lock, and more stringent security measures or further inspection and maintenance are needed; a lower risk value indicates that the security status of the door lock is relatively good and within an acceptable range.

[0110] Determining the risk value means comprehensively considering the specific values ​​of multiple abnormal data and the corresponding abnormal data itself. Different abnormal data may have different degrees of impact on the safe operation of the door lock, thus determining the risk value.

[0111] As an optional embodiment of the present application, S300, determining a risk value based on the specific values ​​of multiple abnormal data of the abnormal cause information and the corresponding abnormal data, includes: S310 , determining abnormality score data corresponding to each abnormal data based on each abnormal data of the abnormality cause information.

[0112] It can be understood that the abnormal score data means that a corresponding numerical value is assigned to each abnormal data according to certain rules or standards. For example, if a continuous high-decibel abnormal sound signal appears in the environmental voiceprint data, and the sound signal is judged to be directly related to the door lock abnormality, the environmental voiceprint data may be given a higher abnormal score data, such as 80 points (assuming the score range is 0 to 100 points) based on factors such as the intensity and duration of the sound and in accordance with pre-set scoring rules.

[0113] Determining anomaly score data involves collecting various anomaly data related to the causes of anomalies in smart door locks, such as environmental soundprint data and lock tongue force data. Because different types of data have different dimensions and value ranges, they need to be standardized to enable comparison and analysis on the same scale. For example, a Z-score normalization method can be used: subtract the mean of the anomaly score dataset from each anomaly score data set, then divide it by the standard deviation of the anomaly score dataset. This results in a normalized anomaly score data set with a mean of 0 and a standard deviation of 1.

[0114] S320: Determine a risk value based on the specific values ​​of the plurality of abnormal data in the abnormal cause information and the abnormality score data of each abnormal data.

[0115] As you can understand, calculating the risk value by comprehensively considering the specific values ​​and anomaly score data of multiple abnormal data means that the analysis is not based on a single data or a certain type of data, but on a combination of the two.

[0116] Abnormal data with large specific values ​​indicates that the abnormality reflected in the data is numerically prominent and may have a significant impact on the normal operation of the door lock. For example, if the specific value of the lock tongue force data is far beyond the normal range, it indicates that the lock tongue may have been subjected to a large external force, which poses a significant threat to the security of the door lock. This specific value plays an important role in calculating the risk value.

[0117] Abnormal data with a high anomaly score indicates that the abnormal situation represented by the data is considered to be more serious from the overall assessment perspective, and its proportion will also be increased when determining the risk value. For example, a high anomaly score for environmental voiceprint data may be due to the detection of continuous high-decibel abnormal sounds, which suggests that there may be factors in the surrounding environment that interfere with the door lock, and this factor will be taken into account when calculating the risk value.

[0118] Through a certain algorithm or model, the specific values ​​and abnormal score data of all abnormal data are integrated and calculated, and finally a value that can comprehensively reflect the degree of risk faced by the smart door lock under the current abnormal situation is obtained, namely the risk value.

[0119] Formula such as: Suppose there are n abnormal data, for the i-th abnormal data, its specific value is , the abnormal score data is , then the risk value The calculation formula is: In this formula: The specific value of each abnormal data is multiplied by the abnormal score data and then summed up, which reflects the weighted effect of the specific value on the abnormal score data. The larger the specific value, the greater the contribution of the corresponding abnormal score data to the total. It is the sum of all the outliers and is used for normalization to ensure that the risk value is within a reasonable range and to avoid the relativity of the final result being affected by the sum of the outliers. For example, there are three outliers with the following outliers: , , , the corresponding anomaly score is , , , then the risk value is calculated as follows: By adopting the above steps S310 to S320, it is helpful to determine the risk value of the smart door lock, and the accuracy of risk value calculation is improved through dynamic specific values ​​and unified unit abnormal scoring data.

[0120] S400: Determine whether to initiate emergency measures based on the risk value.

[0121] It can be understood that initiating emergency measures means that the smart door lock is facing a higher security risk or is in a dangerous state where it may fail. At this time, a series of pre-prepared response measures need to be initiated, such as local sound and light alarms and APP notifications, locking the door lock and recording video evidence, remote alarms and continuous recording.

[0122] Determining whether to initiate emergency measures is based on a comparison between the risk value and the preset threshold of the smart door lock. If the risk value exceeds a certain set higher threshold, it means that the current controller detects that the risk has reached a relatively serious level. At this time, it is necessary to initiate corresponding emergency measures to deal with possible problems or dangerous situations to minimize losses, ensure safety, or restore the smart door lock to normal status. For example, for a smart door lock, emergency operations such as triggering an alarm to notify the user and automatically locking the door to prevent unauthorized entry may be triggered. If the risk value is lower than the set threshold, it means that the current risk is within an acceptable range. The controller detects that no special emergency measures are needed for the time being and can continue to maintain normal operation and monitoring status.

[0123] As an optional embodiment of the present application, S400, determining whether to initiate emergency measures based on the risk value, includes: S410: Perform difference analysis based on the risk value and a preset threshold to obtain the risk abnormality deviation of the abnormal data.

[0124] It can be understood that differential analysis means calculating the difference between the risk value and the preset threshold. For example, if the risk value is , the preset threshold is , then the difference .

[0125] The risk anomaly deviation is a quantitative indicator used to describe the degree of difference between the risk status reflected by abnormal data and the normal expectation (represented by a preset threshold). The greater the deviation, the greater the difference between the current smart door lock's risk status and the preset normal range, and the smart door lock may face more serious anomalies or potential dangers.

[0126] Here is how to calculate the risk anomaly deviation: Risk abnormal deviation = in, represents the actual risk value, Indicates the preset risk threshold.

[0127] The numerator of this formula It is the difference between the actual risk value and the preset threshold, which is used to measure the degree of risk deviation. Yes and The larger value in this way is to normalize the difference so that the result of risk abnormal deviation is The relative degree of risk deviation in different situations can be easily compared and understood.

[0128] For example, if , , then the risk abnormal deviation is , indicating that the actual risk value is 16.7% higher than the preset threshold.

[0129] if , , then the risk abnormal deviation is , indicating that the actual risk value is 20% lower than the preset threshold.

[0130] S420: Determine whether to initiate emergency measures based on the risk abnormality deviation.

[0131] It is understood that based on the obtained risk deviation, a corresponding judgment mechanism will be used to decide whether to initiate emergency measures. Usually, some key deviation thresholds are pre-set.

[0132] If the risk deviation exceeds a certain positive threshold (e.g., a deviation greater than 50%, the specific value is set based on actual conditions), this means the current risk situation has significantly deviated from the normal range and the controller faces a high risk or potential threat. Emergency measures must be initiated to address potential issues and ensure the safe or stable operation of the controller. For example, if a smart door lock controller calculates that the risk deviation exceeds a preset threshold, it may trigger an alarm, automatically lock the door, and other measures.

[0133] When the risk abnormal deviation is less than a lower negative threshold (for example, the deviation is less than 0, which is also set according to actual conditions), it is a relatively safe situation.

[0134] By adopting the above steps S410 to S420, it is helpful to perform difference analysis between the risk value and the preset threshold to obtain the risk abnormal deviation of the abnormal data, and then determine when to initiate emergency measures. The risk abnormal deviation obtained by risk value calculation improves the ability of risk prediction.

[0135] In one possible implementation, S420, based on the risk abnormality deviation, determines whether to initiate emergency measures, including: S421, determine to initiate emergency measures based on the risk abnormal deviation.

[0136] It can be understood that when the risk abnormality deviation is greater than 0, emergency measures are determined to be initiated. S422: Discretization processing is performed according to the risk abnormal deviation to obtain a dynamic response curve.

[0137] Discretization is the process of converting continuous risk anomaly deviation data into discrete data points or intervals. A dynamic response curve represents the discretization of risk anomaly deviation data and then arranging and plotting these discrete data points in chronological or other relevant order.

[0138] A dynamic response curve is formed by connecting these data points sequentially, with time as the horizontal axis (or other logically ordered variables) and the discretized risk anomaly deviation category or value as the vertical axis. This curve shows how the risk anomaly deviation changes over time or other factors, intuitively reflecting the changing risk status of the smart door lock at different times.

[0139] S423, obtaining a dynamic protection characteristic value based on dynamic response curve filtering and fusion; It can be understood that filtering fusion is an operation that processes dynamic response curves. For example, there may be one or two dynamic response curves from different time periods. By fusing these two curves, information about risks over a period of time can be integrated.

[0140] A dynamic protection eigenvalue represents one or a set of eigenvalues ​​extracted from the dynamic response curve after filtering and fusion, representing the controller's current dynamic risk protection status. This eigenvalue provides a high-level summary and abstraction of the processed dynamic response curve, concisely reflecting the controller's protection capabilities and dynamic changes when facing risks. For example, dynamic protection eigenvalues ​​can be values ​​such as the slope, fluctuation range, and average deviation of the curve, derived through further calculation and processing. These values ​​can serve as important basis for subsequent decisions, such as whether to adjust protection strategies or initiate emergency measures.

[0141] S424: Determine the emergency measure level based on the comparison between the dynamic protection characteristic value and the preset range.

[0142] It can be understood that the preset range means that some different range intervals are pre-set, and these range intervals are related to the protection status and emergency response strategy of the controller. Each range interval may correspond to a different degree of risk and corresponding protection requirements. For example, "Level 1 Response", "Level 2 Response", "Level 3 Response", etc. may be set, and each range has clear numerical boundaries. The emergency measure level indicates the current dynamic protection status of the controller, such as local sound and light alarms and APP notifications, locking the door lock and recording video evidence, remote alarm and continuous recording.

[0143] Determining the emergency response level refers to determining the corresponding emergency response level based on the preset range within which the dynamic protection feature value falls. Different ranges correspond to different levels of emergency response, with higher levels typically requiring more stringent and comprehensive emergency response measures to address the current risk. For example, a Level 1 response involves a local audible and visual alarm and app notification, a Level 2 response involves locking the door and recording video evidence, and a Level 3 response involves a remote alarm and continuous video recording.

[0144] By adopting the above steps S421 to S424, it is helpful to dynamically initiate emergency measures based on the risk abnormal deviation. By discretizing the risk abnormal deviation, a dynamic response curve is obtained, and the dynamic response curve is filtered and fused to obtain a dynamic protection characteristic value. The dynamic protection characteristic value is then compared with a preset range to determine the level of emergency measures and thereby obtain the dynamic response capability of the controller in the face of risks.

[0145] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0146] Corresponding to the smart door lock abnormal behavior detection method described in the above embodiment, the embodiment of the present application also provides a smart door lock abnormal behavior detection device, and each unit of the device can implement each step of the smart door lock abnormal behavior detection method. Figure 5 A structural block diagram of the intelligent door lock abnormal behavior detection device provided in an embodiment of the present application is shown. For the sake of convenience, only the parts related to the embodiment of the present application are shown.

[0147] Reference Figure 5 , the device comprises: a determination unit, configured to obtain abnormality cause information when determining that an abnormality occurs in the door lock; wherein the abnormality cause information includes a plurality of abnormality data, at least two of which are environmental soundprint data and lock tongue force data; An analyzing unit, configured to determine, based on the environmental voiceprint data, specific values ​​of a plurality of the abnormal data of the abnormal cause information; a detection unit, configured to determine a risk value based on a plurality of specific values ​​of the abnormal data of the abnormal cause information and the corresponding abnormal data; A result unit is used to determine whether to initiate an emergency measure based on the risk value.

[0148] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of this application. Their specific functions and technical effects can be found in the method embodiment section and will not be repeated here.

[0149] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0150] The embodiment of the present application also provides a smart door lock, Figure 6 This is a schematic diagram of the structure of the smart door lock provided by an embodiment of the present application. Figure 6 As shown, the smart door lock 6 of this embodiment includes: at least one processor 60 ( Figure 6 Only one is shown), at least one memory 61 ( Figure 6 Only one is shown in the figure) and a computer program 62 stored in the at least one memory 61 and executable on the at least one processor 60. When the processor 60 executes the computer program 62, the smart door lock 6 implements the steps of any of the above-mentioned smart door lock abnormal behavior detection method embodiments, or implements the functions of each module / unit in the above-mentioned device embodiments.

[0151] For example, the computer program 62 may be divided into one or more modules / units, which are stored in the memory 61 and executed by the processor 60 to implement the present application. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program 62 in the electronic device 6.

[0152] The smart door lock 6 can be a face recognition lock, a password lock, a fingerprint lock, etc. The smart door lock may include, but is not limited to, a processor 60 and a memory 61. Those skilled in the art will understand that Figure 6 It is only an example of the smart door lock 6 and does not constitute a limitation of the smart door lock 6. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, it may also include input and output devices, network access devices, buses, etc.

[0153] The processor 60 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0154] In some embodiments, the memory 61 may be an internal storage unit of the smart door lock 6, such as a hard drive or memory of the smart door lock 6. In other embodiments, the memory 61 may also be an external storage device of the smart door lock 6, such as a plug-in hard drive, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the smart door lock 6. Furthermore, the memory 61 may include both the internal storage unit of the smart door lock 6 and an external storage device. The memory 61 is used to store an operating system, application programs, a boot loader, data, and other programs, such as the program code of the computer program. The memory 61 may also be used to temporarily store data that has been output or is about to be output.

[0155] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0156] An embodiment of the present application provides a computer program product. When the computer program product is run on a smart door lock, the smart door lock implements the steps in any of the above method embodiments.

[0157] If the integrated unit is implemented as a software functional unit and sold or used as a standalone product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the process steps in the above-mentioned method embodiments by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When executed by a processor, the computer program can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium can include at least: any entity or device capable of carrying the computer program code to the smart door lock, a recording medium, computer memory, read-only memory (ROM), random access memory (RAM), an electrical carrier signal, a telecommunications signal, and a software distribution medium. Examples include a USB flash drive, a removable hard drive, a magnetic disk, or an optical disk.

[0158] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0159] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0160] In the embodiments provided in this application, it should be understood that the disclosed devices / smart door locks and methods can be implemented in other ways. For example, the device / smart door lock embodiments described above are merely illustrative. For example, the division of the modules or units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0161] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0162] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A method for detecting abnormal behavior of a smart door lock, characterized in that: Applied to a smart door lock, the smart door lock includes a door lock body, a sound sensor provided on the door lock body, and a pressure sensor provided on a lock tongue of the door lock body, the method includes: When it is determined that the door lock is abnormal, the abnormal cause information is obtained; wherein the abnormal cause information includes multiple abnormal data, at least two of which are environmental soundprint data and lock tongue force data; Determining, based on the environmental voiceprint data, unique values ​​of a plurality of the abnormal data of the abnormal cause information; Determine a risk value based on the specific values ​​of the plurality of abnormal data of the abnormal cause information and the corresponding abnormal data; Determining whether to initiate emergency measures is based on the risk value.

2. The method for detecting abnormal behavior of a smart door lock according to claim 1, characterized in that: If the door lock is abnormal, obtain the abnormality cause information, including: When it is determined that the door lock is abnormal, activating the sound sensor and the pressure sensor; The sound sensor and the pressure sensor are used to respectively obtain the environmental soundprint data and the lock tongue force data of the abnormal cause information in real time.

3. The method for detecting abnormal behavior of a smart door lock according to claim 1, characterized in that: Determining the unique values ​​of the plurality of abnormal data of the abnormal cause information based on the environmental voiceprint data includes: Determining the types of interference options present in the environment where the smart door lock is located based on the environmental voiceprint data; wherein the types of interference options include passing vehicles, renovations, and thunderstorms; The basic values ​​corresponding to the plurality of abnormal data are adjusted based on the interference option type to obtain the specific values ​​of the plurality of abnormal data of the abnormal cause information.

4. The method for detecting abnormal behavior of a smart door lock according to claim 3, characterized in that: Determining the type of interference options existing in the environment where the smart door lock is located based on the environmental voiceprint data includes: Performing voiceprint feature extraction based on the environmental voiceprint data to obtain voiceprint feature data of the environmental voiceprint data; Obtaining a voiceprint feature template for each type of interference option type; Obtaining a cross-correlation coefficient between the voiceprint feature data and each of the voiceprint feature templates according to the voiceprint feature data and the voiceprint feature templates; Based on the cross-correlation coefficient, the interference option type corresponding to the environmental voiceprint data is matched in the database; wherein the database includes multiple preset cross-correlation coefficients and corresponding interference option types.

5. The method for detecting abnormal behavior of a smart door lock according to claim 4, characterized in that: Obtaining the interference option type corresponding to the environmental voiceprint data by matching in a database based on the cross-correlation coefficient includes: When the interference option type corresponding to the environmental voiceprint data is found to be decoration based on the cross-correlation coefficient, a corresponding time domain signal is determined according to the lock tongue force data, and a corresponding time domain signal is determined according to the environmental voiceprint data; Performing a fast Fourier transform based on the time domain signal of the lock tongue force data and the time domain signal of the environmental soundprint data to obtain the frequency spectrum data of the lock tongue force data and the frequency spectrum data of the environmental soundprint data when the interference option type is decoration; Draw corresponding spectrum curves based on the spectrum data of the lock tongue force data and the spectrum data of the environmental voiceprint data; The decoration interference type of the environment where the smart door lock is located is determined according to the spectrum curve corresponding to the spectrum data of the lock tongue force data and the spectrum data of the environmental soundprint data, and the decoration interference type includes: near-point decoration interference and far-point decoration interference.

6. The method for detecting abnormal behavior of a smart door lock according to claim 5, characterized in that: Adjusting the basic values ​​corresponding to the plurality of abnormal data based on the interference option type to obtain the specific values ​​of the plurality of abnormal data of the abnormal cause information includes: When the decoration interference type is near-point decoration interference, adjusting the base values ​​of the environmental soundprint data and the lock tongue force data based on a set environmental soundprint threshold and a set lock tongue force threshold, respectively, to obtain a specific value of the environmental soundprint data and a specific value of the lock tongue force data; In the case where the decoration interference type is far-point decoration interference, the actual environmental soundprint threshold of the environmental soundprint data and the actual lock tongue force threshold of the lock tongue force data are obtained according to the spectrum curve, and the basic values ​​of the environmental soundprint data and the lock tongue force data are adjusted based on the actual environmental soundprint threshold and the actual lock tongue force threshold to obtain the specific value of the environmental soundprint data and the specific value of the lock tongue force data.

7. The method for detecting abnormal behavior of a smart door lock according to claim 3, characterized in that: The method further comprises: adjusting the basic values ​​corresponding to the plurality of abnormal data based on the interference option type to obtain the specific values ​​of the plurality of abnormal data of the abnormal cause information; determining, based on the interference option type, from among the abnormal data, the abnormal data associated with the interference option type; determining an abnormal behavior degree value according to the abnormal data associated with the interference option type; The basic value corresponding to the abnormal data associated with the interference option type is adjusted based on the abnormal behavior degree value to obtain multiple specific values ​​of the abnormal data of the abnormal cause information.

8. The method for detecting abnormal behavior of a smart door lock according to claim 7, characterized in that: Determining an abnormal behavior degree value according to the abnormal data associated with the interference option type includes: determining a relative error of the abnormal data associated with the interference option type according to an absolute value of a difference between the abnormal data associated with the interference option type and a corresponding preset threshold, and a ratio of the abnormal data associated with the interference option type to the corresponding preset threshold; A normalization process is performed based on the relative error to determine an abnormal behavior degree value.

9. The method for detecting abnormal behavior of a smart door lock according to claim 1, characterized in that: Determining a risk value based on the specific values ​​of the plurality of abnormal data in the abnormal cause information and the corresponding abnormal data includes: Determine the abnormality score data corresponding to each abnormal data based on each abnormal data of the abnormal cause information; A risk value is determined based on the specific values ​​of the plurality of abnormal data and the abnormality score data of each abnormal data in the abnormal cause information.

10. The method for detecting abnormal behavior of a smart door lock according to any one of claims 1 to 9, characterized in that: Determining whether to initiate emergency measures based on the risk value includes: Performing a difference analysis based on the risk value and a preset threshold to obtain a risk abnormality deviation of the abnormal data; Based on the risk abnormal deviation, determine whether to initiate emergency measures.

Images